© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2774
    Prev
    Next
    INDEX
    Explanations

    invitations for interaction or contribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage audience participation and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELD
    -0.82
    quickShipAvailable
    -0.70
     Relief
    -0.67
    fam
    -0.66
    alia
    -0.65
    ĸļ
    -0.64
    LCS
    -0.64
    lehem
    -0.62
     culminating
    -0.62
    bush
    -0.61
    POSITIVE LOGITS
     roam
    1.15
     improv
    1.15
     disagree
    1.10
     explore
    1.09
     ignore
    1.06
     criticize
    1.06
     indulge
    1.06
     pursue
    1.01
     speculate
    1.01
     modify
    1.00
    Activations Density 0.086%

    No Known Activations